© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11247
    Prev
    Next
    INDEX
    Explanations

    report analysis questions, statements, or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.20
     people
    -1.20
     they
    -1.18
     to
    -1.17
     because
    -1.13
    そして
    -1.13
    チューム
    -1.07
     various
    -1.06
     just
    -1.05
    Beskrivning
    -1.05
    POSITIVE LOGITS
    <blockquote>
    1.63
     bestaande
    1.23
    seitigen
    1.19
     gericht
    1.18
     zowel
    1.17
     gevol
    1.13
     betreffende
    1.13
    ことも
    1.13
     gede
    1.12
     zeven
    1.11
    Activations Density 0.022%

    No Known Activations